Using a similarity metric in that multimodal embedding space, we perform mining of audio in German, French, Spanish and English from Librivox against billions of sentences from CommonCrawl.

Finally, we describe the training setup for our back-translation experiments. We continue to differentiate our method from other existing works. Our method does not train multiple peer models with EM training either. In each round, a forward (or backward) model takes turn to play the "back-translation" role to train The role is switched in the next round. In other words, source and target are identical.

Our method is applicable to all NMT models. It does not require extra monolingual data like back-translation, nor does it add more computations and parameters like ensembles ofmodels.